Multi-Image Generation (doubao-seedream-4-5)
Given a prompt, the model will generate multiple sequential images. Related guide: Image GenerationEndpoint
POST /v1/images/generations
Authentication
All requests require a Bearer token in the Authorization header:Request Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | The ID of the model to use, e.g., doubao-seedream-4-5-251128 |
| prompt | string | Yes | Text prompt for generating images, supports both Chinese and English |
| size | string | No | Image size specification. Method 1: Resolution options 1K, 2K, 4K. Method 2: Width x Height pixels (default: 2048x2048). Area range: [1024x1024, 4096x4096], aspect ratio range: [1/16, 16] |
| sequential_image_generation | string | No | Controls multi-image generation. auto: Model automatically determines whether to return multiple images based on prompt. disabled: Only generates one image. Default: disabled |
| sequential_image_generation_options | object | No | Options for sequential image generation, including max_images to set maximum number of images |
| stream | boolean | No | Enable streaming output mode. Default: false |
| response_format | string | No | Output format. url: Returns downloadable jpeg image links (valid for 24 hours). b64_json: Returns Base64 encoded JSON. Default: url |
| watermark | boolean | No | Whether to add watermark. true: Adds “AI Generated” watermark at bottom right. false: No watermark. Default: true |